Back to skill

Security audit

ui-debug-methodology

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed UI debugging checklist with no executable code, persistence, credential access, or unrelated behavior.

Installers should expect this skill to make the agent slow down and inspect UI behavior with DevTools or Playwright before editing. It may activate for many frontend issues because its trigger wording is broad, but the behavior is transparent and limited to ordinary debugging practice.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The description is written to require this methodology in Chinese-language form and does not indicate any user language choice or opt-in. Under the policy, forcing a specific language or locale without user choice is a natural-language policy violation unless clearly justified as region-specific.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The trigger section says the skill must activate for generic situations like 'UI behavior not as expected', 'layout broken', and after a first failed fix attempt. These conditions are broad and common in everyday frontend work, but the file does not give exclusion conditions or negative examples to clarify when the skill should not activate.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.